zhifu gao commited on
Commit ·
b8b7ac6
1
Parent(s): e711f3d
docs: add tested Transformers PR install command
Browse files
README.md
CHANGED
|
@@ -35,6 +35,13 @@ Fun-ASR-Nano is an end-to-end speech recognition model by [FunAudioLLM](https://
|
|
| 35 |
|
| 36 |
Fun-ASR-Nano support is being added to Transformers in [huggingface/transformers#46180](https://github.com/huggingface/transformers/pull/46180). Until it is included in a Transformers release, use a build containing that PR.
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
```python
|
| 39 |
import torch
|
| 40 |
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
|
|
|
|
| 35 |
|
| 36 |
Fun-ASR-Nano support is being added to Transformers in [huggingface/transformers#46180](https://github.com/huggingface/transformers/pull/46180). Until it is included in a Transformers release, use a build containing that PR.
|
| 37 |
|
| 38 |
+
With [PyTorch installed for your platform](https://pytorch.org/get-started/locally/), install the tested PR build and the quickstart dependencies:
|
| 39 |
+
|
| 40 |
+
```bash
|
| 41 |
+
python -m pip install accelerate librosa \
|
| 42 |
+
"transformers @ https://github.com/huggingface/transformers/archive/d58b6371091473c7bd1486f3147950c6e076ace9.zip"
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
```python
|
| 46 |
import torch
|
| 47 |
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
|